added michele notebook

3 years ago · 3854e03d10
parent 7b948bb29e
commit 3854e03d10
5 changed files with 55264 additions and 52504 deletions
--- a/notebooks/01-AM-Exploration.ipynb
+++ b/notebooks/01-AM-Exploration.ipynb
--- a/notebooks/01.1-MB-Exploration_WorksSource.ipynb
+++ b/notebooks/01.1-MB-Exploration_WorksSource.ipynb
--- a/notebooks/02-MM-Cluster_validation.ipynb
+++ b/notebooks/02-MM-Cluster_validation.ipynb
--- a/notebooks/03-Supervised.ipynb
+++ b/notebooks/03-Supervised.ipynb
--- a/src/data/make_dataset.py
+++ b/src/data/make_dataset.py
@ -125,6 +125,7 @@ def main(input_filepath, output_filepath, external_filepath):
    df['primary_email_domain'] = df[df.primary_email.notna()]['primary_email'].apply(lambda x: x.split('@')[1])
    df['other_email_domains'] = df[df.other_emails.notna()]['other_emails'].apply(lambda x: extract_email_domains(x))
    df['url_domains'] = df[df.urls.notna()]['urls'].apply(lambda x: extract_url_domains(x))
+    df['other_url_domains'] = df[df.other_urls.notna()]['other_urls'].apply(lambda x: extract_url_domains(x))
    
    logger.info('Creating simple numeric columns')
    df['n_emails'] = df.other_emails.str.len()